Yen-Shan Chen
PulseAugur coverage of Yen-Shan Chen — every cluster mentioning Yen-Shan Chen across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New metric "Expected Harm" challenges LLM safety evaluations
A new research paper proposes a metric called "Expected Harm" to re-evaluate how the safety of large language models is assessed. The authors argue that current methods overemphasize the severity of harmful outputs whil…
-
New research tackles LLM safety with adaptive guardrails and tool-use trajectory benchmarks
Researchers have developed novel approaches to enhance the safety of large language models (LLMs) by addressing their static nature and the challenges posed by multi-step tool-calling trajectories. One system, SESG, dem…
-
New 'Eyes-on-Me' method enables scalable RAG system poisoning
Researchers have developed a new method called "Eyes-on-Me" to more effectively poison retrieval-augmented generation (RAG) systems. This technique decomposes adversarial documents into reusable "Attention Attractors" a…
-
New audio watermark survives neural codec compression
Researchers have developed Latent-Mark, a novel zero-bit audio watermarking framework designed to overcome the limitations of neural audio codecs. Unlike previous methods vulnerable to neural compression, Latent-Mark em…